Add hierarchical calculation with test ancestors to MetricTemplate1

metric_template_1.py

@@ -15,6 +15,7 @@
 
 import evaluate
 import datasets
+import ham
 
 
 # TODO: Add BibTeX citation
@@ -70,15 +71,17 @@ class MetricTemplate1(evaluate.Metric):
             citation=_CITATION,
             inputs_description=_KWARGS_DESCRIPTION,
             # This defines the format of each prediction and reference
-            features=datasets.Features({
-                'predictions': datasets.Value('int64'),
-                'references': datasets.Value('int64'),
-            }),
+            features=datasets.Features(
+                {
+                    "predictions": datasets.Value("int64"),
+                    "references": datasets.Value("int64"),
+                }
+            ),
             # Homepage of the module for documentation
             homepage="http://module.homepage",
             # Additional links to the codebase or references
             codebase_urls=["http://github.com/path/to/codebase/of/new_module"],
-            reference_urls=["http://path.to.reference.url/new_module"]
+            reference_urls=["http://path.to.reference.url/new_module"],
         )
 
     def _download_and_prepare(self, dl_manager):
@@ -89,7 +92,26 @@ class MetricTemplate1(evaluate.Metric):
     def _compute(self, predictions, references):
         """Returns the scores"""
         # TODO: Compute the different scores of the module
-        accuracy = sum(i == j for i, j in zip(predictions, references)) / len(predictions)
+        accuracy = sum(i == j for i, j in zip(predictions, references)) / len(
+            predictions
+        )
+
+        ancestors = {  # The ancestors for each class, excluding the root
+            "G": {"B", "C", "E"},
+            "F": {"C"},
+        }
+
+        # Calculate hierarchical measures
+        hP, hR, hF = ham.hierarchical_precision_recall_fmeasure(
+            references, predictions, ancestors
+        )
+        print(f"Hierarchical Precision (hP): {hP}")
+        print(f"Hierarchical Recall (hR): {hR}")
+        print(f"Hierarchical F-measure (hF): {hF}")
+
         return {
             "accuracy": accuracy,
-        }
+            "hierarchical_precision": hP,
+            "hierarchical_recall": hR,
+            "hierarchical_fmeasure": hF,
+        }